Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the read-only, idempotent safety profile, but the description adds substantial behavior beyond that: members are a live lens rather than a pinned list, the published version resolves by default, summarized kinds are omitted from members and reported under summarized_kinds with members_complete=false, and count can exceed members length. These are exactly the surprises an agent needs to know about.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The definition leads with the core claim (live resolved set) and then layers the important caveats about summarized kinds. It is dense but largely load-bearing; a few clauses (the parenthetical about blog datafiles, the repeated draft-preview phrasing also present in the schema) could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a fan-out resolution tool, the description covers the semantics, default version resolution, the truncation/summarization contract, the count-vs-length discrepancy, and the escape hatch to sibling list tools. An output schema exists, so the description does not need to explain return shapes, and it still sketches the member record shape usefully.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description restates the version parameter's default-resolution semantics that the schema already documents ('omit (0) for the current one ... preview a draft's members before publishing'), and adds no detail about slug versus app_id beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Resolve an app's LIVE member set') and immediately clarifies that this is not the stored rules but the resolved union of the selector's matches. This clearly distinguishes it from get_app/get_app_version (which return the rule definitions) and from list_datafiles (which lists a single kind).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use it ('see or verify what an app contains'), when to use a sibling instead ('To see the items of a summarized kind, call that kind's own list tool ... e.g. list_datafiles'), and warns what it will not do ('never pages a whole collection'). It also explains that passing version previews a draft's members before publishing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.